January 17, 2018
linear \(\Rightarrow\) non-linear
additive \(\Rightarrow\) interactions
theory-driven \(\Rightarrow\) optimization-driven <
A client wants you to predict data scientist salaries with machine learning.
Kaggle conducted an industry-wide survey of data scientists. https://www.kaggle.com/kaggle/kaggle-survey-2017
Information asked:
Contains information from Kaggle ML and Data Science Survey, 2017, which is made available here under the Open Database License (ODbL).
Client: “There is a problem with the model!”
“What problem?”
Client: “The older the candidates, the higher the predicted salaries.”
Looking inside the black box
Goldstein, A., Kapelner, A., Bleich, J., & Pitkin, E. (2013). Peeking Inside the Black Box: Visualizing Statistical Learning with Plots of Individual Conditional Expectation, 1–22. https://doi.org/10.1080/10618600.2014.907095
Friedman, J. H. (1999). Greedy Function Approximation : A Gradient Boosting Machine. North, 1(3), 1–10. https://doi.org/10.2307/2699986
Client: “We want to understand the model better!”
Breiman, Leo. “Random forests.” Machine learning 45.1 (2001): 5-32.
| Gender | .y.hat |
|---|---|
| Male | 50564.82 |
| Female | 47168.67 |
| Non-binary, genderqueer, or gender non-conforming | 49904.63 |
| A different identity | 49589.76 |
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. Retrieved from http://arxiv.org/abs/1602.04938
IF \(90m^2\leq \text{size} < 110m^2\) AND location \(=\) “good” THEN rent is between 1540 and 1890 EUR
TODO: Example for CNNs
TODO: Example for text (RNNs and attention?)
TODO: PDP gif
TODO: Feature importance figure
TODO: Graphic for counterfactuals
TODO: Graphic for prototypes
More on interpretable machine learning in my book http://christophm.github.io/interpretable-ml-book/.